© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 41652
    Prev
    Next
    INDEX
    Explanations

    code files path

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -0.09
    -0.09
    ↵
    -0.08
    /
    -0.08
    ...
    -0.07
     (
    -0.07
    +
    -0.07
    _
    -0.06
    -
    -0.06
    [
    -0.06
    POSITIVE LOGITS
    éĺħè¯»æľ¬æĸĩåīį
    0.10
    åĽŀçŃĶéĩı
    0.10
    (MPI
    0.10
    [of
    0.10
    ofday
    0.10
    /of
    0.10
    æĺ¯ä½ķåIJ«ä¹ī
    0.10
    (KP
    0.10
    portlet
    0.09
    ঢ
    0.09
    Activations Density 0.106%

    No Known Activations